INDEX

Explanations

occurrences of the word "in" across various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.getElementsBy

-0.15

 Junk

-0.14

wind

-0.14

roids

-0.14

eh

-0.14

uido

-0.14

ÙĬÙĥØ§

-0.14

raq

-0.14

oi

-0.13

arts

-0.13

POSITIVE LOGITS

strup

0.15

 Ð»ÑĮ

0.15

adir

0.14

fo

0.14

ynomial

0.14

ãĥ¼ãĥĨ

0.14

 last

0.13

 chall

0.13

usch

0.13

Activations Density 0.147%

occurrences of the word "in" across various contexts

No Comments

No Known Activations